© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58435
    Prev
    Next
    INDEX
    Explanations

    data packets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¹°
    -0.09
    íķĺìĭ¤
    -0.09
    _INLINE
    -0.09
    IMG
    -0.09
    å²©çŁ³
    -0.08
    çĤŃ
    -0.08
    éĥĩ
    -0.08
    鸷
    -0.08
    око
    -0.08
     недо
    -0.08
    POSITIVE LOGITS
    DataStream
    0.10
    åħ·ä½ĵåĨħ容
    0.09
    Opcode
    0.09
    ura
    0.08
    /data
    0.08
     packet
    0.08
     Vie
    0.08
     bytes
    0.08
    lemen
    0.08
    头éĥ¨
    0.08
    Activations Density 0.510%

    No Known Activations